bakirgrbic commited on
Commit
b36a071
·
verified ·
1 Parent(s): 56ab658

Upload v1 model and tokenizer files

Browse files
Files changed (4) hide show
  1. config.json +29 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "embedding_size": 64,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 196,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 128,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "electra",
16
+ "num_attention_heads": 4,
17
+ "num_hidden_layers": 18,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "summary_activation": "gelu",
21
+ "summary_last_dropout": 0.1,
22
+ "summary_type": "first",
23
+ "summary_use_proj": true,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.51.3",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8ee9170e3178dc882cbf11c3217beb40100a0f220d743c821876715ef16c75
3
+ size 23017856
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-small-discriminator", "tokenizer_class": "ElectraTokenizer"}